© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 70940
    Prev
    Next
    INDEX
    Explanations

    HTML elements or attributes related to icons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̣
    -0.07
    531
    -0.06
    deaux
    -0.06
    Ìĥ
    -0.06
     Shapiro
    -0.06
    683
    -0.06
    186
    -0.06
    563
    -0.06
    627
    -0.06
    åĤ
    -0.06
    POSITIVE LOGITS
     latter
    0.07
    ustin
    0.07
     Kaf
    0.06
    icone
    0.06
    egin
    0.06
     Sok
    0.06
     Bri
    0.06
     Josef
    0.06
    onte
    0.06
    ife
    0.06
    Activations Density 0.000%

    No Known Activations